Gabriele Corso
b4704d94de
Update README.md
2024-09-04 18:44:48 -07:00
Jacob Silterra
9a22cbcbc7
Fix environment.yml
...
Install prody with conda and not pip.
2024-09-04 10:20:46 -04:00
Jacob Silterra
3e80ffd7a0
Merge pull request #241 from bamattsson/fixing_bug_in_atom_preprocessing
...
Fixing bug leading to atom graph containing a lot of incorrect atoms
2024-09-03 15:57:25 -04:00
Jacob Silterra
b65b59aa2e
Merge pull request #248 from juliocesar-io/main
...
Upated docker commands instructions in README.md
2024-09-03 15:56:10 -04:00
Jacob Silterra
5c2e633d22
Merge pull request #236 from burn-in-soul/feat/inits
...
Add __init__ files to all python modules
2024-09-03 15:53:54 -04:00
Julio César
0c1ab6984a
update README with GPU instructions
2024-08-30 16:54:10 +00:00
Julio César
a95a6b8c6d
fix docker build command in README.md
2024-08-30 14:13:33 +00:00
Bjorn Mattsson
8c0b943f1b
changing zero to nan to allow filtering of nan in new_extract_receptor_structure
2024-07-15 15:17:36 +01:00
Gabriele Corso
6d065cd78c
fix issue with different sequences and order
2024-07-08 14:12:59 +02:00
Alexander Schepetilnikov
be0f0f59cf
Add __init__ files to all python modules. There were import failures in some cases, when project not in root directory without own virtual env
2024-06-20 17:15:12 +03:00
Jacob Silterra
a487ef897e
Pin setuptools version
2024-06-10 12:44:45 -04:00
Jacob Silterra
9d0bf3d884
Set any nans/infs in model scores to a small value.
...
With some low (but non-trivial) frequency, processing through the convolutional layers diverge and node attributes become a mixture of nan and inf (which seem to all turn to nan). This later throws an exception during the Kabsch transform, which ruins results for the whole complex. Setting these to 0 basically skips an iteration, at worst it ruins one of the sampled complexes, but leaves the others. Note this is only applied to the main model, *not* the confidence model.
2024-06-10 12:44:45 -04:00
Jacob Silterra
5238b18d4a
Merge pull request #222 from satishgaurav/patch-1
...
fix a typo in readme
2024-05-06 14:32:18 -04:00
Satish Gaurav
a87faaff2b
fix a typo
2024-05-05 14:48:59 +05:30
Jacob Silterra
561f70a897
Various bugfixes
...
* Ensure we calculate rotatable bonds on the version of the ligand with no hydrogens. Also fix spelling of rotable -> rotatable. Closes GH-220 (@Nobody-Zhang)
* Vectorize SO3 calculations. Closes PR GH-218 (@tornikeo)
* Pin pytorch-lightning version. Closes GH-193 (@mikael-h-christensen)
* Guard against divide by zero in torus.py. Closes GH-161 (@amorehead)
* Update e3nn version to 0.5.1. Closes GH-155 (@amorehead)
* Add a little more info on docker container to README.md
2024-04-30 10:00:31 -04:00
Jacob Silterra
2c867df9b8
Improve memory efficiency of graph convolution operation.
2024-04-25 11:13:02 -04:00
Jacob Silterra
3995b24fcd
Improved logging
...
* Change many print statements to logging statements, for better control
* Save log file to web app zip file for easier debugging
2024-04-25 11:06:31 -04:00
Jacob Silterra
e259429889
Add example CSV file
...
Meant to rename it earlier, accidentally just removed it.
2024-04-09 11:03:39 -04:00
Gabriele Corso
6f5d4b152b
Update README.md
2024-03-04 16:20:26 -08:00
Jacob Silterra
0b0f6765f1
Fix conda install instructions in README.
...
Closes #GH-185
2024-03-04 12:42:54 -05:00
Jacob Silterra
df3708b822
Break from download loop once the model has been downloaded.
2024-03-04 12:42:54 -05:00
Gabriele Corso
ff4ad1b5f8
Merge pull request #188 from BioinfoMachineLearning/amorehead-patch-inference-args
...
Rename `inference_args.yaml` to `default_inference_args.yaml` in `README.md`
2024-03-03 21:44:06 -05:00
Alex Morehead
94a6d29ec9
Update README.md
2024-03-03 18:41:24 -06:00
Alex Morehead
3964223733
Rename inference_args.yaml to default_inference_args.yaml
2024-03-03 18:39:54 -06:00
Alex Morehead
59b9313ac3
Rename default_inference_args.yaml to inference_args.yaml
2024-03-03 17:41:55 -06:00
Jacob Silterra
d3791a885e
Add examples
2024-02-28 13:10:12 -05:00
Jacob Silterra
ecfc98083c
Minor bugfix in Dockerfile (old paths)
2024-02-28 12:48:31 -05:00
Jacob Silterra
8c36c48ad1
Merge pull request #182 from gcorso/dev_v1.1
...
Version 1.1
2024-02-28 11:44:07 -05:00
Jacob Silterra
d9114a44ae
Add Dockerfile for creating container.
...
Also add web app code for simple gradio app.
Refine requirements.txt/environment.yml.
Automatically download models if not present.
2024-02-28 11:37:18 -05:00
Gabriele Corso
001c4fa46e
first commit v1.1
2024-02-28 11:21:46 -05:00
Gabriele Corso
bc6b515145
Update README.md
2023-10-12 14:25:03 -07:00
Gabriele Corso
600a23fa23
Fix ckpt path #85
2023-07-18 01:40:55 -07:00
Gabriele Corso
2782769ccd
added code to align apo with holo structures
2023-07-03 09:13:10 +02:00
Gabriele Corso
7dc84c9269
Update environment #74
2023-06-16 02:05:26 -07:00
Gabriele Corso
3d45728415
fix inference_utils.py #90
2023-06-08 05:13:04 -07:00
Hannes Stärk
1b9a9cb09b
Update inference_utils.py for issue #90
2023-05-12 13:58:25 -04:00
Hannes Stärk
6c3d8ceb6e
Update evaluate.py to non-hardcoded split path
2023-05-12 13:44:27 -04:00
Hannes Stärk
81ff501e20
Update evaluate_files.py with non-hard coded paths
2023-05-12 13:41:34 -04:00
Gabriele Corso
c1abe25540
Update README.md
2023-04-13 13:16:51 -07:00
Gabriele Corso
3c3c728cf2
Merge pull request #93 from duerrsimon/patch-1
...
Remove hyperparameter notice
2023-03-27 15:37:02 -04:00
Simon Duerr
23e1dba5d0
Remove hyperparameter notice
...
Due to a runtime error I had to update the space to pin pytorch geometric to 2.1.0 and also updated the space to run with the same default options as described here, so I think this notice can be removed. I keep the number of samples at 10 for now due to runtime constraints but people can set it higher if they want.
I think the colab notebook also needs to fix the dependency, it threw a few errors when I tried it earlier: `pip install git+https://github.com/pyg-team/pytorch_geometric.git@2.1.0
`
2023-03-26 22:58:54 +02:00
Gabriele Corso
f135e3baa7
Update README.md
2023-03-25 12:15:55 -07:00
Gabriele Corso
2c7d438516
Fix path in model parameters #80
2023-03-09 15:12:47 -08:00
Gabriele Corso
73ef67ffcf
fix testset csv and removed raise #77
2023-03-04 14:16:35 -05:00
Gabriele Corso
3829a23af8
Update README.md
2023-02-20 11:10:19 -08:00
Gabriele Corso
dde480d709
small fix
2023-02-11 12:39:27 -05:00
Gabriele Corso
b7259b9584
add example
2023-02-11 12:33:49 -05:00
Gabriele Corso
83993e9ee5
remove odd_parity #76
2023-02-11 12:11:18 -05:00
Gabriele Corso
1f63eb8b37
fix new version
2023-02-11 12:07:56 -05:00
Gabriele Corso
510e51690a
new version: integrated ESM + ESMFold
2023-02-10 19:56:03 -05:00
